dr-housemd commited on
Commit
8cacb95
·
verified ·
1 Parent(s): fbeb814

Upload 10 files

Browse files
README.md CHANGED
@@ -1,3 +1,10 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
1
+ Mistral v3 Tekken or Metharme.
2
+
3
+ Can think via \<thinking\> or \<think\>
4
+
5
+ Just like Roci X but better.
6
+
7
+ (Model card still a WIP)
8
+
9
+ FP16: https://huggingface.co/TheDrummer/Rocinante-XL-16B-v1
10
+ GGUF: https://huggingface.co/TheDrummer/Rocinante-XL-16B-v1-GGUF
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mistralai/Mistral-Nemo-Instruct-2407",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 5120,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 131072,
15
+ "model_type": "mistral",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 54,
18
+ "num_key_value_heads": 8,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_theta": 1000000.0,
21
+ "sliding_window": null,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.45.2",
25
+ "use_cache": true,
26
+ "vocab_size": 131072,
27
+ "quantization_config": {
28
+ "quant_method": "exl3",
29
+ "version": "0.0.32",
30
+ "bits": 6.0,
31
+ "head_bits": 8,
32
+ "calibration": {
33
+ "rows": 250,
34
+ "cols": 2048
35
+ },
36
+ "out_scales": "always",
37
+ "codebook": "mcg"
38
+ }
39
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef696e39097087d8f4944c6619ab5f44a49652792fc733195ad1ecfe6127d7d9
3
+ size 8505777166
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73273a6f518542cc924b836b572d4aa34046abf45e419a19db527a343869d97b
3
+ size 4560182811
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
quantization_config.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff